Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that express preference or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ins
    -0.87
    on
    -0.79
     ?>">
    -0.73
    in
    -0.70
    ink
    -0.66
    jan
    -0.62
     Ingram
    -0.62
    inspec
    -0.61
    us
    -0.60
    del
    -0.59
    POSITIVE LOGITS
    ized
    1.07
    ]--;
    1.03
     ***/
    0.99
    othesis
    0.98
    addContainerGap
    0.98
    ividual
    0.95
     voren
    0.95
    substack
    0.95
    Ārējās
    0.94
    RetentionPolicy
    0.94
    Act Density 0.092%

    No Known Activations